Please use this identifier to cite or link to this item:
|Title:||Monte Carlo Value Iteration with macro-actions||Authors:||Lim, Z.W.
|Issue Date:||2011||Citation:||Lim, Z.W.,Hsu, D.,Lee, W.S. (2011). Monte Carlo Value Iteration with macro-actions. Advances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems 2011, NIPS 2011. ScholarBank@NUS Repository.||Abstract:||POMDP planning faces two major computational challenges: large state spaces and long planning horizons. The recently introduced Monte Carlo Value Iteration (MCVI) can tackle POMDPs with very large discrete state spaces or continuous state spaces, but its performance degrades when faced with long planning horizons. This paper presents Macro-MCVI, which extends MCVI by exploiting macro-actions for temporal abstraction. We provide sufficient conditions for Macro-MCVI to inherit the good theoretical properties of MCVI. Macro-MCVI does not require explicit construction of probabilistic models for macro-actions and is thus easy to apply in practice. Experiments show that Macro-MCVI substantially improves the performance of MCVI with suitable macro-actions.||Source Title:||Advances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems 2011, NIPS 2011||URI:||http://scholarbank.nus.edu.sg/handle/10635/40743||ISBN:||9781618395993|
|Appears in Collections:||Staff Publications|
Show full item record
Files in This Item:
There are no files associated with this item.
checked on May 22, 2019
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.